benchmark_pandas.py

def benchmark_pandas():
    import timerit
    import pandas as pd
    import numpy as np
    column_data = {
        key: np.random.rand(1000)
        for key in map(chr, range(ord('a'), ord('z')))
    }
    data_frame = pd.DataFrame(column_data)

    print('\n-----')

    for timer in timerit.Timerit(100, bestof=10, label='Row Access (PANDAS.loc)'):
        with timer:
            for i in range(len(data_frame)):
                data_frame.loc[i]
    # Timed best=99.227 ms, mean=101.046 ± 1.6 ms for Row Access (PANDAS.loc)

    for timer in timerit.Timerit(100, bestof=10, label='Row Access (PANDAS.iloc)'):
        with timer:
            for i in range(len(data_frame)):
                data_frame.iloc[i]
    # Timed best=81.863 ms, mean=83.144 ± 1.2 ms for Row Access (PANDAS)

    for timer in timerit.Timerit(100, bestof=10, label='Row Access (PANDAS.iterrows)'):
        with timer:
            for row in data_frame.iterrows():
                pass
    # Timed best=23.664 ms, mean=23.948 ± 0.3 ms for Row Access (PANDAS.iterrows)

    for timer in timerit.Timerit(100, bestof=10, label='Row Access (DICT)'):
        with timer:
            for i in range(len(data_frame)):
                {k: column_data[k][i] for k in column_data.keys()}
    # Timed best=4.151 ms, mean=4.271 ± 0.1 ms for Row Access (DICT)

    print('\n-----')

    for timer in timerit.Timerit(100, bestof=10, label='Column Access (PANDAS)'):
        with timer:
            for k in data_frame.keys():
                data_frame[k]
    # Timed best=72.979 µs, mean=74.541 ± 1.0 µs for Column Access (PANDAS)

    for timer in timerit.Timerit(100, bestof=10, label='Column Access (DICT)'):
        with timer:
            for k in column_data.keys():
                column_data[k]
    # Timed best=2.548 µs, mean=2.577 ± 0.0 µs for Column Access (DICT)